This paper addresses the identification of toxic, engaging, and fact-claiming comments on social media. We used the dataset made available by the organizers of the GermEval2021 shared task containing over 3,000 manually annotated Facebook comments in
German. Considering the relatedness of the three tasks, we approached the problem using large pre-trained transformer models and multitask learning. Our results indicate that multitask learning achieves performance superior to the more common single task learning approach in all three tasks. We submit our best systems to GermEval-2021 under the team name WLV-RIT.
In this paper we present UPAppliedCL's contribution to the GermEval 2021 Shared Task. In particular, we participated in Subtasks 2 (Engaging Comment Classification) and 3 (Fact-Claiming Comment Classification). While acceptable results can be obtaine
d by using unigrams or linguistic features in combination with traditional machine learning models, we show that for both tasks transformer models trained on fine-tuned BERT embeddings yield best results.
The study aimed to identify the impact of social networking on the values and
behaviors among university "Face book" Students sites model "
To achieve the objectives of the study were a number of questions as follows:
1- What are the main qualitat
ive characteristics of the members of the study sample?
2- What are the habits and patterns of use of university students to the social
networking site "Face book
3- What are the main pros and cons of using university students to site "Face book"?
4- Do you use the site "Face book" and exposure to its contents helps university students to
link the values?
5- Does it help the site "Face book" university students to overcome some of the
negative behaviors.
And to answer the questions of the study was the use of a questionnaire included
several axes, according to the objectives of the study, and the study included all students
enrolled in the University of Damascus community in the year 2016 Aldrase2015.
